Site-specific weed management using multispectral Unmanned Aerial Vehicle (UAV) in the rice field
2023
Rosle, R. | Che' Ya, N.N. | Berahim, Z. | Roslin, N.A. | Omar, M.H. | Zakaira, N.I. | Ismail, M.R.
Weeds are wild plant populations competing with crops for nutrients, sunlight, and space, negatively affecting crop quality and yield. Depending on the variety of rice used, weed species, and environmental factors, the direct yield loss can range from 16 to 86%. Furthermore, the overuse of chemicals will severely impact crop output, the environment, and the economy. These issues can be overcome through a map-based system. This study aims to detect and map weed distribution using multispectral imagery. The study area for this research is located at Tunjang, Jitra, Kedah, managed by Muda Agriculture Develoment Authority (MADA), and transplanted rice plant variety of Putra 1 was used in the experiment. This study used a drone with a multispectral camera attached that can measure in five wavelengths; blue (B), green (G), Red (R), Red Edge (RE), and Near InfraRed (NIR) was flown around 9 am at 20m above the ground with spatial resolution 1.39cm. The classification method used in this study was Maximum Likelihood, and the processing was conducted using remote sensing software ENVI. The result shows that the overall accuracy (OA) is 98. 67% with a kappa coefficient of 0.9642. Farmers could save approximately 38.39% of herbicide consumption based on the weed map produced by controlling weeds in the study area. The findings of this study show the high accuracy of weed mapping and monitoring capabilities of multispectral UAVs, making them a promising tool for weed management and conservation initiatives.
Afficher plus [+] Moins [-]Mots clés AGROVOC
Informations bibliographiques
Cette notice bibliographique a été fournie par University of the Philippines at Los Baños
Découvrez la collection de ce fournisseur de données dans AGRIS